Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a significant impact or lasting effect on experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alink
    -0.15
    loh
    -0.15
    opper
    -0.14
    .metro
    -0.14
    .fil
    -0.14
    eturn
    -0.14
    StringEncoding
    -0.14
    acin
    -0.13
    770
    -0.13
    otos
    -0.13
    POSITIVE LOGITS
     impact
    0.63
    impact
    0.57
     Impact
    0.57
    Impact
    0.55
     impression
    0.48
     impacts
    0.44
     impressions
    0.38
     effect
    0.37
    å½±åĵį
    0.31
     Impress
    0.31
    Act Density 0.126%

    No Known Activations